A Neural Affinity Framework for Abstract Reasoning: Diagnosing the Compositional Gap in Transformer Architectures via Procedural Task Taxonomy

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ingram, Miguel, Merritt III, Arthur Joseph
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Computation and Language Machine Learning 68T05, 68T27
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CLMN: Concept based Language Models via Neural Symbolic Reasoning
di: Yang, Yibo
Pubblicazione: (2025)

An Automatic Text Classification Method Based on Hierarchical Taxonomies, Neural Networks and Document Embedding: The NETHIC Tool
di: Lomasto, Luigi, et al.
Pubblicazione: (2026)

DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis
di: Wang, Lei, et al.
Pubblicazione: (2026)

lmfaoooo at SemEval-2026 Task 1: Humor Is an Audience. Preference Modeling for Constrained Humor Generation
di: Tikhonov, Alexey, et al.
Pubblicazione: (2026)

CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density
di: Kaiser, Daniel, et al.
Pubblicazione: (2025)

HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning
di: Hill, Brennen
Pubblicazione: (2025)

No Memorization, No Detection: Output Distribution-Based Contamination Detection in Small Language Models
di: Sela, Omer
Pubblicazione: (2026)

Composition of Relational Features with an Application to Explaining Black-Box Predictors
di: Srinivasan, Ashwin, et al.
Pubblicazione: (2022)

MORABLES: A Benchmark for Assessing Abstract Moral Reasoning in LLMs with Fables
di: Marcuzzo, Matteo, et al.
Pubblicazione: (2025)

From Noise to Diversity: Random Embedding Injection in LLM Reasoning
di: Kim, Heejun, et al.
Pubblicazione: (2026)

BitSkip: An Empirical Analysis of Quantization and Early Exit Composition in Transformers
di: Bhuvaneswaran, Ramshankar, et al.
Pubblicazione: (2025)

An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT
di: Ma, Chong, et al.
Pubblicazione: (2023)

Monotonicity as an Architectural Bias for Robust Language Models
di: Cooper, Patrick, et al.
Pubblicazione: (2026)

Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions
di: Alpay, Faruk, et al.
Pubblicazione: (2025)

Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds
di: Alpay, Faruk, et al.
Pubblicazione: (2026)

FARSIQA: Faithful and Advanced RAG System for Islamic Question Answering
di: Asl, Mohammad Aghajani, et al.
Pubblicazione: (2025)

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters
di: Mutlu, Abdulvahap, et al.
Pubblicazione: (2026)

ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
di: Chen, Yihong, et al.
Pubblicazione: (2022)

Dark LLMs: The Growing Threat of Unaligned AI Models
di: Fire, Michael, et al.
Pubblicazione: (2025)

Co-NAML-LSTUR: A Combined Model with Attentive Multi-View Learning and Long- and Short-term User Representations for News Recommendation
di: Nguyen, Minh Hoang, et al.
Pubblicazione: (2025)

Hybrid Gated Flow (HGF): Stabilizing 1.58-bit LLMs via Selective Low-Rank Correction
di: Pizzo, David Alejandro Trejo
Pubblicazione: (2026)

Strategic Doctrine Language Models (sdLM): A Learning-System Framework for Doctrinal Consistency and Geopolitical Forecasting
di: Imanov, Olaf Yunus Laitinen, et al.
Pubblicazione: (2026)

ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models
di: Miliani, Martina, et al.
Pubblicazione: (2025)

LLMs as Deceptive Agents: How Role-Based Prompting Induces Semantic Ambiguity in Puzzle Tasks
di: Yoo, Seunghyun
Pubblicazione: (2025)

Unraveling Media Perspectives: A Comprehensive Methodology Combining Large Language Models, Topic Modeling, Sentiment Analysis, and Ontology Learning to Analyse Media Bias
di: Jähde, Orlando, et al.
Pubblicazione: (2025)

ARF-RLHF: Adaptive Reward-Following for RLHF through Emotion-Driven Self-Supervision and Trace-Biased Dynamic Optimization
di: Zhang, YuXuan
Pubblicazione: (2025)

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
di: Fu, Tianyu, et al.
Pubblicazione: (2025)

Correct Chains, Wrong Answers: Dissociating Reasoning from Output in LLM Logic
di: Rao, Abinav, et al.
Pubblicazione: (2026)

Extracting Sentence Embeddings from Pretrained Transformer Models
di: Stankevičius, Lukas, et al.
Pubblicazione: (2024)

Rethinking the Multilingual Reasoning Gap with Layer Swap
di: Lasbordes, Maxence, et al.
Pubblicazione: (2026)

Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysis
di: Huang, Donghao, et al.
Pubblicazione: (2026)

Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning
di: Pather, Kaviraj, et al.
Pubblicazione: (2025)

Harnessing non-adversarial robustness in large language models
di: Zhou, Qinghua, et al.
Pubblicazione: (2026)

A General Framework of Epistemic Forgetting and its Instantiation by Ranking Functions
di: Beierle, Christoph, et al.
Pubblicazione: (2025)

How much do LLMs learn from negative examples?
di: Hamdan, Shadi, et al.
Pubblicazione: (2025)

Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs
di: Kaiser, Daniel, et al.
Pubblicazione: (2026)

Reasoning Promotes Robustness in Theory of Mind Tasks
di: de Haan, Ian B., et al.
Pubblicazione: (2026)

Value Lens: Using Large Language Models to Understand Human Values
di: Fernández, Eduardo de la Cruz, et al.
Pubblicazione: (2025)

Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness
di: Basu, Abhinaba, et al.
Pubblicazione: (2026)

Lightweight Transformer Architectures for Edge Devices in Real-Time Applications
di: Samson, Hema Hariharan
Pubblicazione: (2026)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
ui	"standard"
language	"it"
VUFIND_SESSION	"a5738a277746488b1f7aefb35f6d1152"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790843755.4872 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "a5738a277746488b1f7aefb35f6d1152" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"ui=standard; language=it; VUFIND_SESSION=a5738a277746488b1f7aefb35f6d1152"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.216.147"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"60063"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2512_07109/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2512_07109/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790843755.4804
REQUEST_TIME	1790843755

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler